Weights for GAE-64: a ~1B-parameter temporal DiT
(
hidden_size=[768, 2048]
,
depth=[28, 6]
) over a
64-channel
geometry-native latent, at
672×378
and
V=81
, with metric Plücker
camera conditioning and Qwen3-0.6B text.
This repo is self-contained for GAE-64 inference: codec, per-channel latent
statistics, DA3 feature-level stats, and the flow transformer. The frozen
DA3-GIANT encoder / DPT head comes from
depth-anything/DA3-GIANT-1.1
.
flow_gae64.pt
— drop-in checkpoint for
gae.load_flow
Runs of TencentARC GAE-D64-1B on huggingface.co
0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About GAE-D64-1B huggingface.co Model
GAE-D64-1B huggingface.co
GAE-D64-1B huggingface.co is an AI model on huggingface.co that provides GAE-D64-1B's model effect (), which can be used instantly with this TencentARC GAE-D64-1B model. huggingface.co supports a free trial of the GAE-D64-1B model, and also provides paid use of the GAE-D64-1B. Support call GAE-D64-1B model through api, including Node.js, Python, http.
GAE-D64-1B huggingface.co is an online trial and call api platform, which integrates GAE-D64-1B's modeling effects, including api services, and provides a free online trial of GAE-D64-1B, you can try GAE-D64-1B online for free by clicking the link below.
TencentARC GAE-D64-1B online free url in huggingface.co:
GAE-D64-1B is an open source model from GitHub that offers a free installation service, and any user can find GAE-D64-1B on GitHub to install. At the same time, huggingface.co provides the effect of GAE-D64-1B install, users can directly use GAE-D64-1B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.